Optimized AI‐Driven Intelligent Transportation Systems for Secure Communication and Traffic Management in Post‐5G Networks

Abstract

ABSTRACT After 5G vehicular networks, an intelligent transportation system with an AI‐based framework encompasses the real‐time traffic management, security, and quality of service for safer communication. This paper proposes a new comprehensive framework for improving vehicular network performance based on state‐of‐the‐art AI‐developed methods such as deep reinforcement learning, edge AI, trust and reputation systems, and dynamic load balancing. The main goal is to enhance security for real‐time vehicular communication while optimizing the vehicular network's efficiency, throughput, latency, and congestion. It leverages a deep reinforcement learning (DRL)‐supported (i.e., involves Q‐learning) routing algorithm for adaptive traffic management, and we show that by integrating edge AI with security‐connected processing into our framework, we can enable real‐time decision‐making. A reputation method is implemented to evaluate the trustworthiness of vehicles in the network. This strategy is one way to affect load balancing as the system is aware of the locations to direct traffic for the purpose of restricting and thus improving throughput. The outcomes demonstrated the significant impact of this architecture because the AI security modules raised the levels of throughput by nearly 15%, whereas the DRL‐based routing improved the overall efficiency and reliability of the network. Moreover, the architecture reveals the possibility of introducing more AI‐based techniques to solve the problems faced by future vehicular communication systems. This serves as a promising starting point to reaching applications that would require less time and be further reliable and more effective. The proposed approach is further validated through comparison with existing routing techniques.